Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SmileyNet -- Towards the Prediction of the Lottery by Reading Tea Leaves with AI

Andreas Birk

TL;DR

The paper provocatively investigates mood-biased AI, introducing SmileyNet, a neural network trained with a smileyfication loss to induce a positive mood and enhance classification. Using a high-fidelity tea-leaf simulation, SmileyNet achieves a coin-flip prediction accuracy of $p_N = 0.7175$, outperforming YOLOv5 ($p=0.53$) and ResNet-34 ($p=0.49$), and shows data-efficient learning with only $100$ training images. The authors extend the approach to lottery forecasting by encoding six numbers with ten SmileyNets per number, yielding $p_{win}=p_N^{10}=0.03615922$, vastly exceeding random chance $p_{chance}=7.15\times10^{-8}$. The work is framed with satirical annotations, highlighting methodological and statistical considerations while exploring the provocative notion of “psychic AI” and its potential, albeit speculative, practical impact.

Abstract

We introduce SmileyNet, a novel neural network with psychic abilities. It is inspired by the fact that a positive mood can lead to improved cognitive capabilities including classification tasks. The network is hence presented in a first phase with smileys and an encouraging loss function is defined to bias it into a good mood. SmileyNet is then used to forecast the flipping of a coin based on an established method of Tasseology, namely by reading tea leaves. Training and testing in this second phase are done with a high-fidelity simulation based on real-world pixels sampled from a professional tea-reading cup. SmileyNet has an amazing accuracy of 72% to correctly predict the flip of a coin. Resnet-34, respectively YOLOv5 achieve only 49%, respectively 53%. It is then shown how multiple SmileyNets can be combined to win the lottery.

SmileyNet -- Towards the Prediction of the Lottery by Reading Tea Leaves with AI

TL;DR

The paper provocatively investigates mood-biased AI, introducing SmileyNet, a neural network trained with a smileyfication loss to induce a positive mood and enhance classification. Using a high-fidelity tea-leaf simulation, SmileyNet achieves a coin-flip prediction accuracy of , outperforming YOLOv5 () and ResNet-34 (), and shows data-efficient learning with only training images. The authors extend the approach to lottery forecasting by encoding six numbers with ten SmileyNets per number, yielding , vastly exceeding random chance . The work is framed with satirical annotations, highlighting methodological and statistical considerations while exploring the provocative notion of “psychic AI” and its potential, albeit speculative, practical impact.

Abstract

We introduce SmileyNet, a novel neural network with psychic abilities. It is inspired by the fact that a positive mood can lead to improved cognitive capabilities including classification tasks. The network is hence presented in a first phase with smileys and an encouraging loss function is defined to bias it into a good mood. SmileyNet is then used to forecast the flipping of a coin based on an established method of Tasseology, namely by reading tea leaves. Training and testing in this second phase are done with a high-fidelity simulation based on real-world pixels sampled from a professional tea-reading cup. SmileyNet has an amazing accuracy of 72% to correctly predict the flip of a coin. Resnet-34, respectively YOLOv5 achieve only 49%, respectively 53%. It is then shown how multiple SmileyNets can be combined to win the lottery.
Paper Structure (8 sections, 7 equations, 5 figures, 3 tables)

This paper contains 8 sections, 7 equations, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. SmileyNet
  3. Related Work
  4. High-Fidelity Simulation
  5. Experiments and Results
  6. SmileyNet for Lottery Forecasts
  7. Conclusions
  8. Acknowledgments

Figures (5)

  • Figure 1: The smiley in form of the Unicode emoticon "U+1F642" that is used to bias the network into a positive mood.
  • Figure 2: YOLOv5 YOLOv5-architecture-2021
  • Figure 3: Resnet DeepLearning-ResNet-CVPR16
  • Figure 4: A real-world example of a tea-leaves-reading image.
  • Figure 5: An illustration of the process that generates the images $I_r$.